Contextual Recurrent Units for Cloze-style Reading Comprehension
This work addresses the challenge of improving contextual modeling in NLP for tasks like sentiment analysis and reading comprehension, representing an incremental advancement by combining existing techniques.
The paper tackles the problem of enhancing local contextual representations in neural networks for NLP tasks by proposing Contextual Recurrent Units (CRU), which integrate CNNs into recurrent units to reduce word ambiguities, and shows significant improvements over traditional and state-of-the-art models in sentiment classification and reading comprehension.
Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks. In this paper, we propose Contextual Recurrent Units (CRU) for enhancing local contextual representations in neural networks. The proposed CRU injects convolutional neural networks (CNN) into the recurrent units to enhance the ability to model the local context and reducing word ambiguities even in bi-directional RNNs. We tested our CRU model on sentence-level and document-level modeling NLP tasks: sentiment classification and reading comprehension. Experimental results show that the proposed CRU model could give significant improvements over traditional CNN or RNN models, including bidirectional conditions, as well as various state-of-the-art systems on both tasks, showing its promising future of extensibility to other NLP tasks as well.